AgentOps API MCP Server

Name: AgentOps API MCP Server
Author: AgentOps-AI

@AgentOps-AI

Repository

About AgentOps API MCP Server

Official MCP server for the AgentOps SDK

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "agentops-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "-m",
        "mcp_server_agentops_api"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is AgentOps API MCP Server?

An MCP server that enables LLM agents to interact with the AgentOps API to access trace data. It provides tools for listing recent traces and retrieving detailed information about specific traces, handling authentication and API communication.

How to use AgentOps API MCP Server?

Configure it as an MCP server in Claude Coder (e.g., in ~/.config/claude-cli/config.yaml) by specifying the server binary path, then run Claude with the --mcp agentops-api flag and include your AgentOps API key in prompts. For standalone use, run ./bin/run-server or uv run -m mcp_server_agentops_api.

Key features of AgentOps API MCP Server

List recent traces from an AgentOps project
Get detailed information about specific traces
Secure two-step authentication (API key → JWT token)
Optional custom API URL for non-production environments
Stateless design – no user data stored between requests

Use cases of AgentOps API MCP Server

An LLM agent asks for the most recent traces in a project
An agent drills into a specific trace to inspect spans and metadata
Debugging agent workflows by fetching trace timing and details
Integrating trace data retrieval into automated agent pipelines

FAQ from AgentOps API MCP Server

What tools does the server provide?

Two tools: list_traces (with parameters AGENTOPS_API_KEY, limit, AGENTOPS_API_URL) and trace_detail (with parameters AGENTOPS_API_KEY, trace_id, AGENTOPS_API_URL).

How does authentication work?

The server requires an AgentOps API key with each request. It exchanges the key for a JWT token, which is used for all authenticated API calls. API keys are never stored between requests.

Where does trace data live?

Data resides in the AgentOps API (production at https://api.agentops.ai by default). The server does not store any data – responses are passed directly to the agent.

What are the runtime dependencies?

The server uses Python and can be run via the provided script (./bin/run-server) or with uv run -m mcp_server_agentops_api. A Docker image can also be built and run.

Can I use a custom API URL?

Yes, both tools accept an optional AGENTOPS_API_URL parameter to override the default production endpoint for local development or staging environments.